Please add a tag indicating where you are taking the course. Choose only one of the platform options in the tag section then the week/module:
- dl-ai-learning-platform
Usual notation for entire dataset stored in a matrix is X. Each row represents a data point. Each column represents a feature.
In DLS Course 1 and Course 2, the notation Professor Ng uses is that each input data sample is a column vector x with dimensions n_x x 1, where n_x is the number of features. Then when we create a matrix with multiple samples, each column is one sample and Professor Ng uses X as name and the dimensions are n_x x m, where m is the number of samples in X.
It is important to realize that this is a choice and the same choice is not made in all of the courses here. You can also arrange the data in the way Balaji describes where each sample is one row of the matrix. You just need to understand which convention is being used in a given situation.